Address:
LIA
339, chemin des Meinajaries
Agroparc BP 1228
84911 AVIGNON Cedex 9
FRANCE
tel : {33,0}4 90 84 35 25
fax : {33,0}4 90 84 35 01
Email : eric.sanjuan(at)univavignon.fr
Who am I?
Coming from the world of discrete mathematics and algebraic logic, I like working on original applications of discrete probabilistic models to Knowledge Representation, Natural Language Processing and related areas in Information Science like Text Mining and Information Retrieval. The goal is to find efficient algorithms to handle discrete aspects of texts like syntax, linguistic rules and underlying conceptual structure.
Bilingual:French/Spanish
Foreign language:
English.
University Degrees
2018
Habilitation in Computer Science,
Avignon Université, France (December 6 2018)
Thesis:
Turing tests in Natural Language Processing and Information Retrieval Contributions to the theory, development and evaluation
of textual information processing systems for decision support
Director:
Patrice Bellot (Aix Marseille Université)
Reviewers:
Jian Yun Nie (Université de Montréal, CA),
Jacques Savoy (Université de Neuchâtel, CH),
Fionn Murtagh (University of Huddersfield, UK)
Academic committee: Jean François Bonastre (LIA, Avignon, President), Josiane Mothe (IRIT, Toulouse), Marie Sylvie Poli (CNE, Avignon), Philippe Mulhem (LIG, Grenoble), Juan Manuel Torres Moreno (LIA, Avignon), Olivier Hamon (Invitee;
Syllabs, Paris)
Academic Supervisor: Tania Jimenez (LIA)
2000
Ph.D in Mathematics and Computer Science, Université
Claude Bernard  Lyon 1, France.
Title: Algèbres de Heyting avec opérateurs booléens et applications aux systèmes d'information.
Directors: Professors Luisa Iturrioz and Maurice Pouzet
1995
M. Phil. in Mathematics (formal Logic option), Université Claude
Bernard  Lyon 1, France.
1994
M.A in Discrete Mathematics,
Université Claude Bernar  Lyon 1, France.
1993
B.A. in Mathematics (Computer Science and Statistics Option), Université
Claude Bernard  Lyon 1, France.
Keywords
Teaching
Computer science: language programming: C, C++, PERL 5, php,
JAVA, LISP; Information systems : relational databases, SQL,
UML; networks: TCP/IP, security based on Open SSL; Operating Systems: LINUX, SOLARIS, UNIX, Windows; General software:
OpenOffice, MSOffice, Apache, MySQL; Specialized software: R,
Splus, SAS, SPSS, WEKA.
Mathematics:
Statistic: descriptive, parametric and non parametric tests;
Data Mining: clustering, classification, principal component
analysis; graph theory; linear algebra.
Research
Text mining: Graph
clustering, Natural Language Processing, Machine Learning,
Information Visualization, Information Retrieval, Automatic
summarization.
Discrete Mathematics : association rules, Lattice Theory, Formal
concept analysis, Horn functions, Rough Sets, algebraic logic.
Teaching history
I am currently a permanent lecturer at the
Institute of Technology of
Avignon in the department of Statistics and Decision Support Systems (StID).
Before coming to Avignon in 2006, I was appointed as an assistant lecturer
first in 2000 at the Institute of Technology 2 in Grenoble,
then in 2001 at the
University Claude Bernard  Lyon 1, and
in 2002 I was nominated as lecturer at the Institute of Technology of Metz.
I'm teaching Computer Science, Information Systems and Data Mining to both under and postgraduated students
in Avignon (StID
and masters of computer science
and Digital Governement)
and in Lyon (Masters of Applied Mathematics).
These lectures address the following topics:
 Data Bases (SQL 2 and 3, MySQL, ORACLE, ODBC, JDBC, PostGreSQL)
 Algorithms and programming (languages C, C++, PERL)
 Information Systems (theory in UML, applications based on XML standard and LAMPS
server: LINUX+ Apache + MySQL + PHP + PERL DBI + SSL )
 Data Mining (R, Splus, Weka, SAS, SPSS)
 Statistic tests for Computer Human Interface evaluation (Masters only)
 Order and Hierarchical Structures (lattices and logic for data mining  Masters only)
 Graph theory, Discrete mathematics and Formal Logic
 Probabilitytheory and Statistic
 Linear algebra
Extended summaries in French and students notes are available at
http://idapa.termwatch.es/
Research activities
My research interests revolve around Discrete Mathematics, Knowledge
Discovery, Natural Language Processing (NLP), Information retrieval and Cultural Heritage.
The phd's I supervised over these topics are listed in theses.fr
Before these projects, I have been working on the theoretical side using algebraic logic formalism:
On the application side I'm developing a complete online text mining system called
TermWatch with Fidelia IbekweSanJuan
 University Lyon 3, France based on Terminology graphs.
Last developments of TermWatch include graph decomposition based on minimal complete separators in collaboration with Anne Berry using the programs by Bangaly Kaba.
I did also considered several NLP applications within the LIA TALNE team including:
 automatic summarization based on statistical physics concepts with
Sylvia Fernandez and
JuanManuel Torres Moreno. You can try this approach here on the INEX 20092010 corpora.
 discourse segmentation based on FreeLing open platform with Iria Da Cunha.
An online application is available here.
 discourse classification based on association rule mining with the IULA team of the University Pompeu Fabra University in Barcelona, Spain.
Organisation of scientific activities
 CLEF MC2 lab that aimed to evaluate microblog retrieval and contextualization.
 CLEF 2018 conference in Avignon.

Guest
editor with Anne Berry and Maurice Pouzet, special issue of journal
Annals of Mathematics and Artificial Intelligence (AMAI) Volume 49,
Knowledge Discovery and Discrete Mathematics: Dedicated to the Memory of Peter L. Hammer,
Numbers 14, pp. 1312, ISSN 10122443, April, 2007
 Reviewer of journals Pattern Recognition Letters, Information Science,
Informetrics, Information Processing & Management, Discrete Mathematics, Discrete Applied Mathematics.